Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr 10;25(8):2412.
doi: 10.3390/s25082412.

An Automated Algorithm for Obstructive Sleep Apnea Detection Using a Wireless Abdomen-Worn Sensor

Thi Hang Dang  1   2 , Seong-Mun Kim  1 , Min-Seong Choi  2 , Sung-Nam Hwan  2 , Hyung-Ki Min  2 , Franklin Bien  1   2
Affiliations

An Automated Algorithm for Obstructive Sleep Apnea Detection Using a Wireless Abdomen-Worn Sensor

Thi Hang Dang et al. Sensors (Basel). .

Abstract

Obstructive sleep apnea (OSA) is common among older populations and individuals with cardiovascular diseases. OSA diagnosis is primarily conducted using polysomnography or recommended home sleep apnea test (HSAT) devices. Wireless wearable devices have emerged as promising tools for OSA screening and follow-up. This study introduces a novel automated algorithm for detecting OSA using abdominal movement signals and acceleration data collected by a wireless abdomen-worn sensor (Soomirang). Thirty-seven subjects underwent overnight monitoring using an HSAT device and the Soomirang system simultaneously. Normal and apnea events were classified using an MLP-Mixer deep learning model based on Soomirang data, which was also used to estimate total sleep time (ST). Pearson correlation and Bland-Altman analyses were conducted to evaluate the agreement of ST and the apnea-hypopnea index (AHI) calculated by the HSAT device and Soomirang. ST demonstrated a correlation of 0.9 with an average time difference of 7.5 min, while AHI showed a correlation of 0.95 with an average AHI difference of 3. The accuracy, sensitivity, and specificity of the Soomirang for detecting OSA were 97.14%, 100%, and 95.45% at AHI ≥ 15, respectively. The proposed algorithm, utilizing data from a wireless abdomen-worn device exhibited excellent performance in detecting moderate to severe OSA. The findings underscored the potential of a simple device as an accessible and effective tool for OSA screening and follow-up.

Keywords: MLP-mixer; abdomen-worn sensor; capacitive sensor; home sleep apnea test; obstructive sleep apnea.

PubMed Disclaimer

Conflict of interest statement

All authors have seen and approved this manuscript. Thi Hang Dang is a postdoctoral researcher in the Department of Electrical Engineering at UNIST, Republic of Korea, and is also a consultant for SB Solutions Inc., UNIST, Republic of Korea. Seong-mun Kim has completed his doctorate at UNIST in February 2025. Min-seong Choi, Sung-nam Hwan, and Hyung-ki Min are employees of SB Solutions Inc. F.B. is a professor in the Department of Electrical Engineering at UNIST, Republic of Korea, and is also the CEO of SB Solutions Inc., UNIST, Republic of Korea.

Figures

Figure 1
Figure 1
Flow chart diagram for OSA detection using Soomirang data. DL model, deep learning model.
Figure 2
Figure 2
Experimental setup for overnight sleep monitoring with the ApneaLink AirTM and Soomirang devices.
Figure 3
Figure 3
Data recordings from a full-night study of a subject were captured using the ApneaLink Air™ (respiratory flow, respiratory effort, and oxygen saturation) and the Soomirang device (capacitance and three-axis acceleration). The red areas alongside the respiratory flow signal were denoted as annotated apnea events extracted from the ApneaLink Air™.
Figure 4
Figure 4
Data recordings from the ApneaLink Air™ (respiratory flow, respiratory effort, and oxygen saturation) and the Soomirang device (capacitance and three-axis acceleration) within a 100-s recording window. The red-highlighted areas along the respiratory flow signal indicate annotated apnea events identified by the ApneaLink Air™.
Figure 5
Figure 5
MLP-Mixer model for apnea/normal classification. GELU, Gaussian Error Linear Unit; MLP, multilayer perceptron.
Figure 6
Figure 6
BiLSTM model for apnea/normal classification: (a) an LSTM cell; (b) BiLSTM model.
Figure 7
Figure 7
Pearson correlations and Bland–Altman plots for a comparison between estimated sleep time extracted from Soomirang (STSoomirang) and evaluation time extracted from ApneaLink AirTM (ETApneaLinkTM), in which n is the number of subjects, r is the correlation coefficient, LOA is the limit of agreement, and SD is the standard deviation. The dotted line in the Pearson correlation plot represents the line of equality, the dotted lines in the Bland-Altman plot indicate the range within which 95% of the differences are expected to fall.
Figure 8
Figure 8
Example of apnea events detected by the Soomirang device compared with those detected by ApneaLink Air™ in an entire recording. Red and blue bars represent apnea events detected by ApneaLink AirTM and Soomirang, respectively.
Figure 9
Figure 9
Example of apnea events detected by the Soomirang device compared with those detected by ApneaLink Air™ in a detailed view of a 30-min data window. Red and blue areas represent apnea events detected by ApneaLink AirTM and Soomirang, respectively.
Figure 10
Figure 10
Pearson correlation and Bland–Altman plots for a comparison between the AHI calculated by Soomirang and ApneaLink AirTM devices: (a) in a five-fold validation and (b) in the test set. The dotted line in the Pearson correlation plot represents the line of equality, the dotted lines in the Bland-Altman plot indicate the range within which 95% of the differences are expected to fall. The character n is the number of subjects, r is the correlation coefficient, LOA is the limit of agreement, and SD is the standard deviation.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Gottlieb D.J., Punjabi N.M. Diagnosis and management of obstructive sleep apnea: A review. JAMA. 2020;323:1389–1400. doi: 10.1001/jama.2020.3514. - DOI - PubMed
    1. Kapur V.K., Auckley D.H., Chowdhuri S., Kuhlmann D.C., Mehra R., Ramar K., Harrod C.G. Clinical practice guideline for diagnostic testing for adult obstructive sleep apnea: An American Academy of Sleep Medicine clinical practice guideline. J. Clin. Sleep Med. 2017;13:479–504. doi: 10.5664/jcsm.6506. - DOI - PMC - PubMed
    1. Yeghiazarians Y., Jneid H., Tietjens J.R., Redline S., Brown D.L., El-Sherif N., Mehra R., Bozkurt B., Ndumele C.E., Somers V.K., et al. Obstructive sleep apnea and cardiovascular disease: A scientific statement from the American Heart Association. Circulation. 2021;144:e56–e67. doi: 10.1161/CIR.0000000000000988. - DOI - PubMed
    1. Osorio R.S., Martínez-García M.Á., Rapoport D.M. Sleep apnoea in the elderly: A great challenge for the future. Eur. Respir. J. 2022;59:2101649. doi: 10.1183/13993003.01649-2021. - DOI - PMC - PubMed
    1. Balagny P., Vidal-Petiot E., Renuy A., Matta J., Frija-Masson J., Steg P.G., Goldberg M., Zins M., D’Ortho M.-P., Wiernik E. Prevalence, treatment and determinants of obstructive sleep apnoea and its symptoms in a population-based French cohort. ERJ Open Res. 2023;9:1. doi: 10.1183/23120541.00053-2023. - DOI - PMC - PubMed

LinkOut - more resources